© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9613
    Prev
    Next
    INDEX
    Explanations

    a variety of relatively common words, with no apparent unifying theme other than perhaps emotionality

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.59
    +#+
    -0.55
    <bos>
    -0.54
     ErrIntOverflow
    -0.54
    \{\\
    -0.54
     gynhyrchwyd
    -0.52
     الرياضيه
    -0.51
    mobileqq
    -0.51
    JspWriter
    -0.47
    ngdoc
    -0.46
    POSITIVE LOGITS
    ExecuteNonQuery
    0.58
    uro
    0.52
     Clues
    0.50
    Magick
    0.49
    CopyWith
    0.49
    videoId
    0.48
    Weiterlesen
    0.47
     fédé
    0.47
    atify
    0.46
    Recuerda
    0.46
    Activations Density 9.685%

    No Known Activations